Elamur Research⌕
☰
home / papers / 2026 / Explainable AI for Ethical Counter Speech Generation in Hate Speech Mitigation

Explainable AI for Ethical Counter Speech Generation in Hate Speech Mitigation

Summary

Automated hate speech moderation usually deletes content or suspends users, and its classifiers rarely justify their decisions. Both habits weaken user trust and miss chances for constructive engagement. The authors propose a three-stage pipeline that pairs transparent detection with counter-speech generation. First, a HateBERT classifier fine-tuned on ToxiGen labels text as toxic or non-toxic. Second, that decision is explained through five complementary XAI techniques: LIME, Integrated Gradients, examination of attention weights, counterfactual probing, and explanations written in natural language. Third, a fine-tuned Llama 3.1-8B-Instruct model uses these explanations, together with CONAN counter-narratives, to write empathetic, fact-based replies aimed at the specific harmful elements found. The authors present this coupling of multi-method explainability with response generation as a novel contribution and claim strong performance suitable for real deployment. However, the quantitative results section was missing from the supplied text, so no figures can be reported here. The work matters because it moves moderation from opaque removal toward explained, dialogue-oriented intervention. The code is publicly released.

Key points

  • Pipeline: HateBERT (detection) → five XAI methods (explanation) → Llama 3.1-8B-Instruct (XAI-informed counter-speech generation).
  • ToxiGen (detection data):
    • over 274,000 GPT-3-generated, human-annotated statements;
    • built with demonstration-based prompting and ALICE;
    • roughly balanced between toxic and benign;
    • covers 13 minority identity groups.
  • CONAN (counter-speech data):
    • 4,078 hate speech/counter-narrative pairs: 1,288 English, 1,719 French, 1,071 Italian;
    • written by more than 100 trained experts.
  • Motivation from related work: attention weights can mislead as explanations, and earlier work on XAI for hate speech applied single methods. This motivates combining several XAI approaches.
  • Code: available at github.com/AshifulRidoy/XAI-on-HateBERT.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/3je3mug9bbb3

@inproceedings{ridoy2026explainable,
  title = {{Explainable AI for Ethical Counter Speech Generation in Hate Speech Mitigation}},
  author = {Ridoy, Ashiful Islam and Faisal, Mohammed and Kumar, Yogesh and Rashid, Md Mamun-Ur and Ernst, Marina and Hopfgartner, Frank},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/3je3mug9bbb3},
  url = {https://doi.org/10.63317/3je3mug9bbb3}
}

References

36 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Helena Bonaldi, Yi-Ling Chung, Gavin Abercrombie, and Marco Guerini. 2024. NLP for counterspeech against hate: A survey and how-to guide. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 3480– 3499, Mexico City, Mexico. Association for Computational Linguistics. find
  2. Tommaso Caselli, Valerio Basile, Jelena Mitrović, and Michael Granitzer. 2021. HateBERT: Retraining BERT for abusive language detection in English. In Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021), pages 17–25, Online. Association for Computational Linguistics. find our card
  3. Sergio Andrés Castaño-Pulgarín, Natalia Suárez-Betancur, Luz Magnolia Tilano Vega, and Harvey Mauricio Herrera López. 2021. Internet, social media and online hate speech. systematic review. Aggression and Violent Behavior, 58:101608. find
  4. Yi-Ling Chung, Elizaveta Kuzmenko, Serra Sinem Tekiroglu, and Marco Guerini. 2019. CONAN - COunter NArratives through nichesourcing: a multilingual dataset of responses to fight online hate speech. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2819… find our card
  5. Kevin Clark, Urvashi Khandelwal, Omer Levy, and Christopher D. Manning. 2019. What does BERT look at? an analysis of BERT’s attention. In Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 276–286, Florence, Italy. Association for Computationa… find
  6. Christopher Clarke, Matthew Hall, Gaurav Mittal, Ye Yu, Sandra Sajeev, Jason Mars, and Mei Chen. 2023. Rule by example: Harnessing logical rules for explainable hate speech detection. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers),… find
  7. Thomas Davidson, Dana Warmsley, Michael Macy, and Ingmar Weber. 2017. Automated hate speech detection and the problem of offensive language. Proceedings of the International AAAI Conference on Web and Social Media, 11(1):512–515. find our card
  8. Antigoni Founta, Constantinos Djouvas, Despoina Chatzakou, Ilias Leontiadis, Jeremy Blackburn, Gianluca Stringhini, Athena Vakali, Michael Sirivianos, and Nicolas Kourtellis. 2018. Large scale crowdsourcing and characterization of twitter abusive behavior. Proceedings of the International AAAI Confe… find
  9. Oguzhan Gencoglu. 2021. Cyberbullying Detection With Fairness Constraints . IEEE Internet Computing, 25(01):20–29. find
  10. Dominik Hangartner, Gloria Gennaro, Sary Alasiri, Nicholas Bahrich, Alexandra Bornhoft, Joseph Boucher, Buket Buse Demirci, Laurenz Derksen, Aldo Hall, Matthias Jochum, Maria Murias Munoz, Marc Richter, Franziska Vogel, Salomé Wittwer, Felix Wüthrich, Fabrizio Gilardi, and Karsten Donnay. 2021. Empa… find
  11. Thomas Hartvigsen, Saadia Gabriel, Hamid Palangi, Maarten Sap, Dipankar Ray, and Ece Kamar. 2022. ToxiGen: A large-scale machine-generated dataset for adversarial and implicit hate speech detection. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1:… find our card
  12. Md. Mehedi Hassan, Anindya Nag, Riya Biswas, Md Shahin Ali, Sadika Zaman, Anupam Kumar Bairagi, and Chetna Kaushal. 2025. Explainable artificial intelligence for natural language processing: A survey. Data Knowledge Engineering, 160:102470. find
  13. Md Saroar Jahan and Mourad Oussalah. 2023. A systematic review of hate speech automatic detection using natural language processing. Neurocomputing, 546:126232. find
  14. Sarthak Jain and Byron C. Wallace. 2019. Attention is not Explanation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 3543–3556, Minneapolis, Minnesota. Associa… find our card
  15. Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. 2016. A diversity-promoting objective function for neural conversation models. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pag… find our card
  16. Chin-Yew Lin. 2004. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out, pages 74–81, Barcelona, Spain. Association for Computational Linguistics. find
  17. Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. In International Conference on Learning Representations. find
  18. Binny Mathew, Navish Kumar, Ravina, Pawan Goyal, and Animesh Mukherjee. 2018. Analyzing the hate and counter speech accounts on twitter. ArXiv, abs/1812.02712. — [arXiv:1812.02712](https://arxiv.org/abs/1812.02712) find
  19. Harshkumar Mehta and Kalpdrum Passi. 2022. Social media hate speech detection using explainable artificial intelligence (xai). Algorithms, 15(8). find
  20. Ioannis Mollas, Zoe Chrysopoulou, Stamatis Karlos, and Grigorios Tsoumakas. 2020. Ethos: a multi-label hate speech detection dataset. Complex & Intelligent Systems, pages 1–16. find
  21. Ayushi Nirmal, Amrita Bhattacharjee, Paras Sheth, and Huan Liu. 2024. Towards interpretable hate speech detection using large language model-extracted rationales. In Proceedings of the 8th Workshop on Online Abuse and Harms (WOAH 2024), pages 223–233, Mexico City, Mexico. Association for Computation… find
  22. Juri Opitz. 2024. Schroedinger’s threshold: When the AUC doesn’t predict accuracy. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 14400–14406, Torino, Italia. ELRA and ICCL. find
  23. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pages 311–318, Philadelphia, Pennsylvania, USA. Association for Computational… find our card
  24. Jing Qian, Anna Bethke, Yinyin Liu, Elizabeth Belding, and William Yang Wang. 2019. A benchmark dataset for learning to intervene in online hate speech. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Lan… find our card
  25. Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2016. "why should i trust you?": Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’16, page 1135–1144, New York, NY, USA. Association for Co… find our card
  26. Mukund Sundararajan, Ankur Taly, and Qiqi Yan. 2017. Axiomatic attribution for deep networks. In International Conference on Machine Learning. find
  27. Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. 2014. Sequence to sequence learning with neural networks. In Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 2, NIPS’14, page 3104–3112, Cambridge, MA, USA. MIT Press. find
  28. Serra Sinem Tekiroğlu, Yi-Ling Chung, and Marco Guerini. 2020. Generating counter narratives against online hate speech: Data and strategies. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1177–1190, Online. Association for Computational Linguistics… find
  29. Guy Tevet and Jonathan Berant. 2021. Evaluating the evaluation of diversity in natural language generation. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 326–346, Online. Association for Computational Linguistics. find
  30. United Nations. What is hate speech? \| United Nations — un.org. https://www.un.org/en/hate-speech/understanding-hate-speech/what-is-hate-speech. [Accessed 08-10-2025]. ↗
  31. Bertie Vidgen, Tristan Thrush, Zeerak Waseem, and Douwe Kiela. 2021. Learning from the worst: Dynamically generated datasets to improve online hate detection. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Nat… find our card
  32. Yongjin Yang, Joonkee Kim, Yujin Kim, Namgyu Ho, James Thorne, and Se-Young Yun. 2023. HARE: Explainable hate speech detection with step-by-step reasoning. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 5490–5505, Singapore. Association for Computational Linguistics. find
  33. Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger, and Yoav Artzi. 2019. Bertscore: Evaluating text generation with bert. ArXiv, abs/1904.09675. find
  34. Zhixue Zhao, Ziqi Zhang, and Frank Hopfgartner. 2022. Utilizing subjectivity level to mitigate identity term bias in toxic comments classification. Online Soc. Networks Media, 29:100205. find
  35. Yi Zheng, Björn Ross, and Walid Magdy. 2023. What makes good counterspeech? a comparison of generation approaches and evaluation metrics. In Proceedings of the 1st Workshop on CounterSpeech for Online Abuse (CS4OA), pages 62–71, Prague, Czechia. Association for Computational Linguistics. find
  36. Wanzheng Zhu and Suma Bhat. 2021. Generate, prune, select: A pipeline for counterspeech generation against online hate speech. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 134–149, Online. Association for Computational Linguistics. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/ridoy-2026-explainable-ai-ethical-counter-speech/